cure-policy-guard

Complete product engineering skill library — 104 skills (domain-organized), 41 agents (engineering, product, marketing, business, data, security), 4 personas (cross-domain engagement archetypes), 11 rules, 9 output styles, multi-layer hooks with agent auto-triggering, bundled stdlib Python tooling, LSP server configs (MCP is an opt-in template, not shipped). Standards for Android, iOS, Web, Firebase, Python, Go, Rust, Docker, Terraform, and cloud infrastructure.

104 skills · 41 agents · hooks · LSP

Opt-in multi-vendor orchestration: Claude architect, Codex implementation and correctness lanes (codex exec), Antigravity system-review lane (agy) in read-only worktrees, and a fresh-context advisor. Uses existing ChatGPT and Google logins; independent of cure-product-engineering.

1 skill · 4 agents · hooks

Mod: caps how many subagents one session runs at once, tracked by agent id from spawn to completion; optional research routing to a model alias, off by default. Adds /agents-budget.

Mod: prompt cache time left, hit rate and misses above the prompt; says what a cold next message re-caches. Adds /cache.

Mod: checks file:line citations in Claude's answers against the session's repositories and toasts the stale ones; never edits the answer. Adds /cite-check.

Mod: draws the images you sent above the prompt until the turn that carried them ends.

Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Claude Code mod: watch Headroom snip tokens off every request, with an animated band, a /headroom log and a running total.

Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production hardening.

8 skills · 1 MCP server

Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin — decisions are policy-gated before they run and every decision produces a tamper-evident receipt verifiable offline.

1 skill · 2 commands · 2 agents · hooks

Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.

9 skills · 5 MCP servers